Multi-scale Feature Extraction Module Research Articles

SCPMan: Shape context and prior constrained multi-scale attention network for pancreatic segmentation

Due to the poor prognosis of Pancreatic cancer, accurate early detection and segmentation are critical for improving treatment outcomes. However, pancreatic segmentation is challenged by blurred boundaries, high shape variability, and class imbalance. To tackle these problems, we propose a multiscale attention network with shape context and prior constraint for robust pancreas segmentation. Specifically, we proposed a Multi-scale Feature Extraction Module (MFE) and a Mixed-scale Attention Integration Module (MAI) to address unclear pancreas boundaries. Furthermore, a Shape Context Memory (SCM) module is introduced to jointly model semantics across scales and pancreatic shape. Active Shape Model (ASM) is further used to model the shape priors. Experiments on NIH and MSD datasets demonstrate the efficiency of our model, which improves the state-of-the-art Dice Score for 1.01% and 1.03% respectively. Our architecture provides robust segmentation performance, against the blurry boundaries, and variations in scale and shape of pancreas.

A multi-step loss meta-learning method based on multi-scale feature extraction for few-shot fault diagnosis

Existing deep learning (DL) algorithms are based on a large amount of training data and they face challenges in effectively extracting fault features when dealing with few-shot fault diagnoses. Model-agnostic meta-learning (MAML) also faces some challenges, including the limited capability of the basic convolutional neural network (CNN) with a single convolutional kernel to extract fault features comprehensively, as well as the instability of model training due to the inner and outer double-layer loops. To address these issues, this paper presents a multi-step loss meta-learning method based on multi-scale feature extraction (MFEML). Firstly, an improved multi-scale feature extraction module (IMFEM) is designed to solve the problem of the insufficient feature extraction capability of the CNN. Secondly, the multi-step loss is used to reconstruct the meta-loss to address the issue of MAML training instability. Finally, the experimental results of two datasets demonstrate the effectiveness of the MFEML.

Fault Diagnosis of Rotating Machinery Bearings Based on Multi-Scale Attention Feature Fusion under Few Shot and Complex Working Conditions

Accidents caused by failures in rotating machinery bearings have heightened attention in bearing failure diagnosis. Scholars have explored methods to build fault diagnosis models to tackle the challenge of creating diagnostic models with few bearing failure samples available. However, many diagnostic models may suffer from overfitting issues under insufficient samples, affecting fault diagnosis performance. Additionally, rotating machinery operates under changing, complex conditions and noise interference, further deteriorating the effectiveness of fault diagnosis. This paper proposes a fault diagnosis model based on multi-scale attentional feature fusion (FD-MSAFF) to address the issue above. This model comprises a multi-scale feature extraction module, an attentional feature fusion module, and an MMD-based weighted prototype network. The FD-MSAFF model improves few-shot learning by using its multi-scale feature extraction and depth-wise separable attention modules to blend multi-scale features effectively with contextual information. It also tackles classification issues in few-shot sizes with its MMD-weighted prototype network, which is less susceptible to noise. Simulated tests under complex scenarios, such as changing conditions, noise variations, cross-bearing conditions, and comparisons with other algorithms, have proven the FD-MSAFF model's superior accuracy and generalization in diagnosing bearing faults in rotating machinery.

FE-FAIR: Feature-Enhanced Fused Attention for Image Super-Resolution

Transformers have performed better than traditional convolutional neural networks (CNNs) for image super-resolution (SR) reconstruction in recent years. Currently, shifted window multi-head self-attention based on the swin transformer is a typical method. Specifically, the multi-head self-attention is used to extract local features in each window, and then a shifted window strategy is used to discover information interaction between different windows. However, this information interaction method needs to be more efficient and include some global feature information, which limits the model’s performance to a certain extent. Furthermore, optimizing the utilization of shallow features, which exhibit significant energy reserves and invaluable low-frequency information, is critical for advancing the efficacy of super-resolution techniques. In order to solve the above issues, we propose the feature-enhanced fused attention (FE-FAIR) method for image super-resolution. Specifically, we design the multi-scale feature extraction module (MSFE) as a shallow feature extraction layer to extract rich low-frequency information from different scales. In addition, we propose the fused attention block (FAB), which introduces channel attention in the form of residual connection based on shifted window self-attention, effectively achieving the fusion of global and local features. Simultaneously, we also discuss other methods to enhance the performance of the FE-FAIR method, such as optimizing the loss function, increasing the window size, and using pre-training strategies. Compared with state-of-the-art SR methods, our proposed method demonstrates better performance. For instance, FE-FAIR outperforms SwinIR by over 0.9 dB when evaluated on the Urban100 (×4) dataset.

HPNet: High precision point cloud registration using feature pyramid and hybrid position encoding

Point cloud registration precision degrades when the scene contains symmetric structures or repeated patches. Also, the common operation of continuous downsampling in existing registration methods causes the loss of detailed information and leads to further registration precision degradation. In this paper, we propose a high precision point cloud registration network (HPNet) to learn discriminative features by considering both multi-scale information and position information. We first propose a multi-scale feature extraction module similar to the feature pyramid that allows the extracted features to contain multi-scale information. Then, an information interaction is performed on the features to learn global contextual information by using Transformer with a hybrid position encoding, which takes into account both absolute and relative positions of points. Finally, the features obtained from the information interaction module are directly used to predict the point correspondences. Comprehensive experiments on 3DMatch, 3DLoMatch, ModelNet, and ModelLoNet datasets demonstrate the state-of-the-art performance of the proposed method and the implementation of HPNet in SLAM shows its effectiveness in real application.

A novel low light object detection method based on the YOLOv5 fusion feature enhancement

Low-light object detection is an important research area in computer vision, but it is also a difficult issue. This research offers a low-light target detection network, NLE-YOLO, based on YOLOV5, to address the issues of insufficient illumination and noise interference experienced by target detection tasks in low-light environments. The network initially preprocesses the input image with an improvement technique before suppressing high-frequency noise and enhancing essential information with C2fLEFEM, a unique feature extraction module. We also created a multi-scale feature extraction module, AMC2fLEFEM, and an attention mechanism receptive field module, AMRFB, which are utilized to extract features of multiple scales and enhance the receptive field. The C2fLEFEM module, in particular, merges the LEF and FEM modules on top of the C2f module. The LEF module employs a low-frequency filter to remove high-frequency noise; the FEM module employs dual inputs to fuse low-frequency enhanced and original features; and the C2f module employs a gradient retention method to minimize information loss. The AMC2fLEFEM module combines the SimAM attention mechanism and uses the pixel relationship to obtain features of different receptive fields, adapt to brightness changes, capture the difference between the target and the background, improve the network's feature extraction capability, and effectively reduce the impact of noise. The AMRFB module employs atrous convolution to enlarge the receptive field, maintain global information, and adjust to targets of various scales. Finally, for low-light settings, we replaced the original YOLOv5 detection head with a decoupled head. The Exdark dataset experiments show that our method outperforms previous methods in terms of detection accuracy and performance.

Convolutional neural network intelligent fault diagnosis method for rotating machinery based on discriminant correlation analysis multi-domain feature fusion strategy

Aiming at solving the problems of limited training data, single input information, and limited diagnostic accuracy under the influence of strong background noise in fault diagnosis of rotating machinery, this paper proposes a fault diagnosis method based on the combination of discriminant correlation analysis (DCA) and convolutional neural network (CNN). Firstly, the original vibration signal is divided into several segments in the time domain, and the training data is directly processed by one CNN branch to extract multi-scale time domain features. Simultaneously, the divided data is subjected to discrete wavelet transform (DWT), and processed by another branch of CNN to extract multi-scale time-frequency features. Then, the DCA feature fusion mechanism is adopted to fuse the two-domain features extracted in the parallel branches to improve the model’ detection ability. Finally, the fused features are input into the deep CNN for training and learning to extract new features and output the classification results. Through the experimental analysis of two different types of data, the results show that the proposed method can be used for fault diagnosis of rotating machinery effectively. Compared with the single CNN network, the proposed method combines the multi-domain multi-scale feature extraction module with the DCA feature fusion module to enrich the feature information extraction ability. At the same time, the network performance is improved to get higher fault classification accuracy higher.

A Semi-Supervised Multi-Scale Deep Adversarial Model for Fan Anomaly Detection

Failure of cooling fan will have a great impact on the operation of the air-conditioning cooling system. Traditional anomaly detection methods for fans rely on manual feature extraction, which is easy to lose effective information. Deep learning-based methods have potential to overcome such a problem, however, it is difficult to train the network without enough monitoring data. In operation, cooling usually worked at high speed, and its monitoring data contain much high-speed rotational noise. This will confuse the networks to focus on high-energy noise while lose the weak but useful information. To solve these problems, we propose a semi-supervised multi-scale deep adversarial model (SMDAM) for fan anomaly detection. In SMDAM, we propose the Linear Spectral Line Elimination (LSLE) technique to reduce the interference of rotational noise spectral lines on network training. Subsequently, a multi-scale feature extraction module is introduced to enrich diagnostic information, which extracts features from different scales without increasing the depth of the convolutional layer. Finally, two engineering data sets are used to verify the superiority of the proposed method. The results show that SMDAM is superior to other methods.

MSV-net: Multi-scale visual-inspired network for short-term electricity price forecasting

In electricity price forecast, deep networks have shown promising due to their strong nonlinear modeling capability but corresponding design tricks are not convincible, reflecting the situation that biologically-inspired networks in time-series analysis are still not enough explored. To this end, this paper proposes a multi-scale visual-inspired network with three explored modules, namely MSV-Net, for electricity price forecasting. In particular, through simulating both the ocular globe and neurons in signal conversion and further enhancement, the multi-scale feature extraction module captures the overall and specific time-scale features via multiple convolutional kernels and especially highlights the core features via self-attention mechanisms. Through imitating the left and right hemispheres in analyzing and producing complementary visual information, the dual-stream collaboration module adopts the convolutional layer and gated recurrent unit to extract and integrate time-dependent relationships in parallel, thus improving the model stability. Through simulating the higher visual region in understanding complex environments, the forecasting module is introduced to forecast the electricity price. The layer-by-layer collaboration of the above three modules guarantees the effectiveness of the MSV-Net. Moreover, four comprehensive evaluation metrics are explored to assess the forecasting performance in peak, low, and normal samples. Experiments and discussions under two electricity price datasets show that the MSV-Net has satisfactory forecasting accuracy and stability, in improving average mean absolute percent error of 31.59 % and 25.15 % for two datasets compared with 12 baselines, and shows extensible in other energy forecasting fields.

OD-MVSNet: Omni-dimensional dynamic multi-view stereo network.

Multi-view stereo based on learning is a critical task in three-dimensional reconstruction, enabling the effective inference of depth maps and the reconstruction of fine-grained scene geometry. However, the results obtained by current popular 3D reconstruction methods are not precise, and achieving high-accuracy scene reconstruction remains challenging due to the pervasive impact of feature extraction and the poor correlation between cost and volume. In addressing these issues, we propose a cascade deep residual inference network to enhance the efficiency and accuracy of multi-view stereo depth estimation. This approach builds a cost-volume pyramid from coarse to fine, generating a lightweight, compact network to improve reconstruction results. Specifically, we introduce the omni-dimensional dynamic atrous spatial pyramid pooling (OSPP), a multiscale feature extraction module capable of generating dense feature maps with multiscale contextual information. The feature maps encoded by the OSPP module can generate dense point clouds without consuming significant memory. Furthermore, to alleviate the issue of feature mismatch in cost volume regularization, we propose a normalization-based 3D attention module. The 3D attention module aggregates crucial information within the cost volume across the dimensions of channel, spatial, and depth. Through extensive experiments on benchmark datasets, notably DTU, we found that the OD-MVSNet model outperforms the baseline model by approximately 1.4% in accuracy loss, 0.9% in completeness loss, and 1.2% in overall loss, demonstrating the effectiveness of our module.

Coronary artery segmentation in CCTA images based on multi-scale feature learning.

Coronary artery segmentation is a prerequisite in computer-aided diagnosis of Coronary Artery Disease (CAD). However, segmentation of coronary arteries in Coronary Computed Tomography Angiography (CCTA) images faces several challenges. The current segmentation approaches are unable to effectively address these challenges and existing problems such as the need for manual interaction or low segmentation accuracy. A Multi-scale Feature Learning and Rectification (MFLR) network is proposed to tackle the challenges and achieve automatic and accurate segmentation of coronary arteries. The MFLR network introduces a multi-scale feature extraction module in the encoder to effectively capture contextual information under different receptive fields. In the decoder, a feature correction and fusion module is proposed, which employs high-level features containing multi-scale information to correct and guide low-level features, achieving fusion between the two-level features to further improve segmentation performance. The MFLR network achieved the best performance on the dice similarity coefficient, Jaccard index, Recall, F1-score, and 95% Hausdorff distance, for both in-house and public datasets. Experimental results demonstrate the superiority and good generalization ability of the MFLR approach. This study contributes to the accurate diagnosis and treatment of CAD, and it also informs other segmentation applications in medicine.

Dual-3DM3AD: Mixed Transformer Based Semantic Segmentation and Triplet Pre-Processing for Early Multi-Class Alzheimer's Diagnosis.

Alzheimer's Disease (AD) is a widespread, chronic, irreversible, and degenerative condition, and its early detection during the prodromal stage is of utmost importance. Typically, AD studies rely on single data modalities, such as MRI or PET, for making predictions. Nevertheless, combining metabolic and structural data can offer a comprehensive perspective on AD staging analysis. To address this goal, this paper introduces an innovative multi-modal fusion-based approach named as Dual-3DM3-AD. This model is proposed for an accurate and early Alzheimer's diagnosis by considering both MRI and PET image scans. Initially, we pre-process both images in terms of noise reduction, skull stripping and 3D image conversion using Quaternion Non-local Means Denoising Algorithm (QNLM), Morphology function and Block Divider Model (BDM), respectively, which enhances the image quality. Furthermore, we have adapted Mixed-transformer with Furthered U-Net for performing semantic segmentation and minimizing complexity. Dual-3DM3-AD model is consisted of multi-scale feature extraction module for extracting appropriate features from both segmented images. The extracted features are then aggregated using Densely Connected Feature Aggregator Module (DCFAM) to utilize both features. Finally, a multi-head attention mechanism is adapted for feature dimensionality reduction, and then the softmax layer is applied for multi-class Alzheimer's diagnosis. The proposed Dual-3DM3-AD model is compared with several baseline approaches with the help of several performance metrics. The final results unveil that the proposed work achieves 98% of accuracy, 97.8% of sensitivity, 97.5% of specificity, 98.2% of f-measure, and better ROC curves, which outperforms other existing models in multi-class Alzheimer's diagnosis.

Multi-Scale Class Attention Network for Diabetes Retinopathy Grading

Article Multi-Scale Class Attention Network for Diabetes Retinopathy Grading Hongyu Chen 1, Ronghua Wu 1, Chen Tao 1, Wenjing Xu 1, Hongzhe Liu 3, Cheng Xu 3, and Muwei Jian 1,2,* 1 School of Information Science and Technology, Linyi University, 276000, China 2 School of Computer Science and Technology, Shandong University of Finance and Economics, 250014, China 3 Beijing Key Laboratory of Information Service Engineering, 100101, Beijing, China * Correspondence: jianmuweihk@163.com Received: 1 June 2023 Accepted: 21 July 2023 Abstract: Diabetes retinopathy (DR) is a universal eye disease, which brings irreversible blindness risks to patients in severe cases. Due to the scarcity of professional ophthalmologists, it has become increasingly important to develop computer-aided diagnostic systems for DR grading diagnosis. However, the current mainstream deep learning methods face challenges in accurately classifying the severity of DR, making it difficult for them to provide a reliable reference for clinicians. To tackle this problem, we propose two novel modules to improve the accuracy of DR classification. Specifically, we design a multi-scale feature extraction module to capture tiny lesions in fundus images and differentiate similar lesions simultaneously. In addition, we develop a class attention module to alleviate the adverse impact of intra-class similarity on DR grading. Experimental results show that our proposed modules attain significant performance improvement on the APTOS2019 blind detection dataset, with accuracy and quadratic weighted Kappa metrics achieving 95.98% and 97.12%, respectively.

Robust Point Cloud Registration Network for Complex Conditions.

Point cloud registration is widely used in autonomous driving, SLAM, and 3D reconstruction, and it aims to align point clouds from different viewpoints or poses under the same coordinate system. However, point cloud registration is challenging in complex situations, such as a large initial pose difference, high noise, or incomplete overlap, which will cause point cloud registration failure or mismatching. To address the shortcomings of the existing registration algorithms, this paper designed a new coarse-to-fine registration two-stage point cloud registration network, CCRNet, which utilizes an end-to-end form to perform the registration task for point clouds. The multi-scale feature extraction module, coarse registration prediction module, and fine registration prediction module designed in this paper can robustly and accurately register two point clouds without iterations. CCRNet can link the feature information between two point clouds and solve the problems of high noise and incomplete overlap by using a soft correspondence matrix. In the standard dataset ModelNet40, in cases of large initial pose difference, high noise, and incomplete overlap, the accuracy of our method, compared with the second-best popular registration algorithm, was improved by 7.0%, 7.8%, and 22.7% on the MAE, respectively. Experiments showed that our CCRNet method has advantages in registration results in a variety of complex conditions.

RealFuVSR: Feature Enhanced Real-World Video Super-Resolution

BackgroundThe recurrent recovery is one of the common methods for video super-resolution, which models the correlation between frames via hidden states. However, when we apply the structure to real-world scenarios, it leads to unsatisfactory artifacts. We found that, in the real-world video super-resolution training, the use of unknown and complex degradation can better simulate the degradation process of the real world. MethodsBased on this, we propose the RealFuVSR model, which simulates the real-world degradation and mitigates the artifacts caused by the video super-resolution. Specifically, we propose a multi-scale feature extraction module(MSF) which extracts and fuses features from multiple scales, it facilitates the elimination of hidden state artifacts. In order to improve the accuracy of hidden states alignment information, RealFuVSR use advanced optical flow-guided deformable convolution. Besides, cascaded residual upsampling module is used to eliminate the noise caused by the upsampling process. ResultsThe experiment demonstrates that our RealFuVSR model can not only recover the high-quality video but also outperform the state-of-the-art RealBasicVSR and RealESRGAN models.

MC-Net: multi-scale contextual information aggregation network for image captioning on remote sensing images

ABSTRACT Remote Sensing Image Captioning (RSIC) plays a crucial role in advancing semantic understanding and has increasingly become a focal point of research. Nevertheless, existing RSIC methods grapple with challenges due to the intricate multi-scale nature and multifaceted backgrounds inherent in Remote Sensing Images (RSIs). Compounding these challenges are the perceptible information disparities across diverse modalities. In response to these challenges, we propose a novel multi-scale contextual information aggregation image captioning network (MC-Net). This network incorporates an image encoder enhanced with a multi-scale feature extraction module, a feature fusion module, and a finely tuned adaptive decoder equipped with a visual-text alignment module. Notably, MC-Net possesses the capability to extract informative multiscale features, facilitated by the multilayer perceptron and transformer. We also introduce an adaptive gating mechanism during the decoding phase to ensure precise alignment between visual regions and their corresponding text descriptions. Empirical studies conducted on four publicly recognized cross-modal datasets unequivocally demonstrate the superior robustness and efficacy of MC-Net in comparison to contemporaneous RSIC methods.

A novel combined probabilistic load forecasting system integrating hybrid quantile regression and knee improved multi-objective optimization strategy

In contemporary power systems, diverse energy integration and technological advancements have complicated load dynamics, revealing limitations in traditional deterministic forecasting techniques. Given the pivotal role of Probabilistic Load Forecasting (PLF) in mitigating risks in power system planning and operation, the pursuit of more accurate PLF techniques has evidently become a topic of paramount importance. Therefore, in this study, a novel hybrid Quantile Regression (QR) model integrating causal dilated convolution, residual connection, and Bidirectional Long Short-Term Memory (BiLSTM) is initially proposed for PLF, its core multi-scale feature extraction module can deeply mine the interactions between loads and their features. However, relying solely on a single-model often encounters inherent flaws in certain scenarios. Recognizing this, a Combined Probabilistic Load Forecasting System (CPLFS) is further proposed. This system incorporates the developed hybrid QR to establish a diversified candidate model pool, aiming to select the top-performing benchmarks in various scenarios and utilizes the Knee enhanced Pareto mechanism to adjust the combined weights of each benchmark, thereby bridging the gap created by the “No Free Lunch (NFL)” phenomenon. Taking the load uncertainty of Australia as an illustrative example, simulations indicate that the hybrid QR outperforms traditional models. Furthermore, CPLFS surpasses the best benchmarks and other combinations in both prediction accuracy and stability.

Multi-View Stereo Network Based on Attention Mechanism and Neural Volume Rendering

Due to the presence of regions with weak textures or non-Lambertian surfaces, feature matching in learning-based Multi-View Stereo (MVS) algorithms often leads to incorrect matches, resulting in the construction of the flawed cost volume and incomplete scene reconstruction. In response to this limitation, this paper introduces the MVS network based on attention mechanism and neural volume rendering. Firstly, we employ a multi-scale feature extraction module based on dilated convolution and attention mechanism. This module enables the network to accurately model inter-pixel dependencies, focusing on crucial information for robust feature matching. Secondly, to mitigate the impact of the flawed cost volume, we establish a neural volume rendering network based on multi-view semantic features and neural encoding volume. By introducing the rendering reference view loss, we infer 3D geometric scenes, enabling the network to learn scene geometry information beyond the cost volume representation. Additionally, we apply the depth consistency loss to maintain geometric consistency across networks. The experimental results indicate that on the DTU dataset, compared to the CasMVSNet method, the completeness of reconstructions improved by 23.1%, and the Overall increased by 7.3%. On the intermediate subset of the Tanks and Temples dataset, the average F-score for reconstructions is 58.00, which outperforms other networks, demonstrating superior reconstruction performance and strong generalization capability.

BFE-Net: Object Detection with Bidirectional Feature Enhancement

In realistic scenarios, existing object detection models still face challenges in resisting interference and detecting small objects due to complex environmental factors such as light and noise. For this reason, a novel scheme termed BFE-Net based on bidirectional feature enhancement is proposed. Firstly, a new multi-scale feature extraction module is constructed, which uses a self-attention mechanism to simulate human visual perception. It is used to capture global information and long-range dependencies between pixels, thereby optimizing the extraction of multi-scale features from input images. Secondly, a feature enhancement and denoising module is designed, based on bidirectional information flow. In the top-down, the impact of noise on the feature map is weakened to further enhance the feature extraction. In the bottom-up, multi-scale features are fused to improve the accuracy of small object feature extraction. Lastly, a generalized intersection over union regression loss function is employed to optimize the movement direction of predicted bounding boxes, improving the efficiency and accuracy of object localization. Experimental results using the public dataset PASCAL VOC2007test show that our scheme achieves a mean average precision (mAP) of 85% for object detection, which is 2.3% to 8.6% higher than classical methods such as RetinaNet and YOLOv5. Particularly, the anti-interference capability and the performance in detecting small objects show a significant enhancement.

Semantic Attention and Structured Model for Weakly Supervised Instance Segmentation in Optical and SAR Remote Sensing Imagery

Instance segmentation in remote sensing (RS) imagery aims to predict the locations of instances and represent them with pixel-level masks. Thanks to the more accurate pixel-level information for each instance, instance segmentation has enormous potential applications in resource planning, urban surveillance, and military reconnaissance. However, current RS imagery instance segmentation methods mostly follow the fully supervised paradigm, relying on expensive pixel-level labels. Moreover, remote sensing imagery suffers from cluttered backgrounds and significant variations in target scales, making segmentation challenging. To accommodate these limitations, we propose a semantic attention enhancement and structured model-guided multi-scale weakly supervised instance segmentation network (SASM-Net). Building upon the modeling of spatial relationships for weakly supervised instance segmentation, we further design the multi-scale feature extraction module (MSFE module), semantic attention enhancement module (SAE module), and structured model guidance module (SMG module) for SASM-Net to enable a balance between label production costs and visual processing. The MSFE module adopts a hierarchical approach similar to the residual structure to establish equivalent feature scales and to adapt to the significant scale variations of instances in RS imagery. The SAE module is a dual-stream structure with semantic information prediction and attention enhancement streams. It can enhance the network’s activation of instances in the images and reduce cluttered backgrounds’ interference. The SMG module can assist the SAE module in the training process to construct supervision with edge information, which can implicitly lead the model to a representation with structured inductive bias, reducing the impact of the low sensitivity of the model to edge information caused by the lack of fine-grained pixel-level labeling. Experimental results indicate that the proposed SASM-Net is adaptable to optical and synthetic aperture radar (SAR) RS imagery instance segmentation tasks. It accurately predicts instance masks without relying on pixel-level labels, surpassing the segmentation accuracy of all weakly supervised methods. It also shows competitiveness when compared to hybrid and fully supervised paradigms. This research provides a low-cost, high-quality solution for the instance segmentation task in optical and SAR RS imagery.